R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering

Abstract

In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et al., 2016) dataset, which provides a pre-selected passage, from which the answer to a given question may be extracted. More recently, researchers have begun to tackle open-domain QA, in which the model is given a question and access to a large corpus (e.g., wikipedia) instead of a pre-selected passage (Chen et al., 2017a). This setting is more complex as it requires large-scale search for relevant passages by an information retrieval component, combined with a reading comprehension model that "reads" the passages to generate an answer to the question. Performance in this setting lags considerably behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader $(R^3)$, based on two algorithmic innovations. First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of generating the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-generation Reader model, based on reinforcement learning. We report extensive experimental results showing that our method significantly improves on the state of the art for multiple open-domain QA datasets.

8 pages, accepted by AAAI 2018

References in corpus (6)

• Large-scale Simple Question Answering with Memory Networks
• Machine Comprehension Using Match-LSTM and Answer Pointer
• Quasar: Datasets for Question Answering by Search and Reading
• Multi-Perspective Context Matching for Machine Comprehension
• Improved Neural Relation Detection for Knowledge Base Question Answering
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension

Cited by in corpus (12)

• Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
• Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering
• Multi-style Generative Reading Comprehension
• Controlling Risk of Web Question Answering
• NLPGym -- A toolkit for evaluating RL agents on Natural Language Processing Tasks
• Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction
• Around the GLOBE: Numerical Aggregation Question-Answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks
• TWEETQA: A Social Media Focused Question Answering Dataset
• JEC-QA: A Legal-Domain Question Answering Dataset
• Learning a Cost-Effective Annotation Policy for Question Answering
• Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation
• Knowledge Efficient Deep Learning for Natural Language Processing